{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:56:53Z","timestamp":1779382613358,"version":"3.53.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729720","type":"print"},{"value":"9783031729737","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72973-7_6","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"89-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Relation DETR: Exploring Explicit Position Relation Prior for\u00a0Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2547-4921","authenticated-orcid":false,"given":"Xiuquan","family":"Hou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0693-6574","authenticated-orcid":false,"given":"Meiqin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5117-3110","authenticated-orcid":false,"given":"Senlin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1710-3818","authenticated-orcid":false,"given":"Badong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3422-944X","authenticated-orcid":false,"given":"Xuguang","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS\u2013improving object detection with one line of code. In: International Conference on Computer Vision, pp. 5561\u20135569 (2017)","DOI":"10.1109\/ICCV.2017.593"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: YOLACT: real-time instance segmentation. In: International Conference on Computer Vision, pp. 9157\u20139166 (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"6_CR3","unstructured":"Cai, Z., Liu, S., Wang, G., Ge, Z., Zhang, X., Huang, D.: Align-DETR: Improving DETR with simple IoU-aware BCE loss. arXiv preprint arXiv:2304.07527 (2023)"},{"key":"6_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"6_CR5","unstructured":"Chen, K., et\u00a0al.: Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Q., et al.: Group DETR: Fast DETR training with group-wise one-to-many assignment. In: International Conference on Computer Vision, pp. 6633\u20136642 (2023)","DOI":"10.1109\/ICCV51070.2023.00610"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Li, L.J., Fei-Fei, L., Gupta, A.: Iterative visual reasoning beyond convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7239\u20137248 (2018)","DOI":"10.1109\/CVPR.2018.00756"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Pan, J., Lei, J., Zeng, D., Wu, Z., Chen, C.: EEE-Net: efficient edge enhanced network for surface defect detection of glass. IEEE Trans. Instrum. Measure\/ (2023)","DOI":"10.1109\/TIM.2023.3320746"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Yang, J., Zhang, P., Yuan, L., Zhang, L.: Dynamic DETR: end-to-end object detection with dynamic attention. In: International Conference on Computer Vision, pp. 2988\u20132997 (2021)","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6_CR12","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"6_CR13","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., Cao, Y.: EVA-02: a visual representation for neon genesis. arXiv preprint arXiv:2303.11331 (2023)","DOI":"10.2139\/ssrn.4813567"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: TOOD: task-aligned one-stage object detection. In: International Conference on Computer Vision, pp. 3490\u20133499. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Hao, X., Huang, D., Lin, J., Lin, C.Y.: Relation-enhanced DETR for component detection in graphic design reverse engineering. In: IJCAI, pp. 4785\u20134793 (2023)","DOI":"10.24963\/ijcai.2023\/532"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109558","volume":"140","author":"X Hou","year":"2023","unstructured":"Hou, X., Liu, M., Zhang, S., Wei, P., Chen, B.: CANet: contextual information and spatial attention based network for detecting small defects in manufacturing industry. Pattern Recogn. 140, 109558 (2023)","journal-title":"Pattern Recogn."},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Hou, X., Liu, M., Zhang, S., Wei, P., Chen, B.: Salience detr: enhancing detection transformer with hierarchical salience filtering refinement. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17574\u201317583 (2024)","DOI":"10.1109\/CVPR52733.2024.01664"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588\u20133597 (2018)","DOI":"10.1109\/CVPR.2018.00378"},{"key":"6_CR22","unstructured":"Hu, Z., Sun, Y., Wang, J., Yang, Y.: DAC-DETR: divide the attention layers and conquer. Adv. Neural Inform. Process. Syst. 36 (2024)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Jia, D., et al.: DETRs with hybrid matching. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 19702\u201319712 (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"6_CR24","unstructured":"Jiang, C., Xu, H., Liang, X., Lin, L.: Hybrid knowledge routed modules for large-scale object detection. Adv. Neural Inform. Process. Syst. 31 (2018)"},{"key":"6_CR25","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4015\u20134026 (2023)"},{"key":"6_CR26","unstructured":"Kolve, E., et\u00a0al.: Ai2-thor: An interactive 3d environment for visual ai. arXiv preprint arXiv:1712.05474 (2017)"},{"key":"6_CR27","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vis."},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: DN-DETR: Accelerate DETR training by introducing query denoising. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"6_CR29","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural Inform. Process. Syst. 33, 21002\u201321012 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"6_CR30","doi-asserted-by":"publisher","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: European Conference on Computer Vision, pp. 280\u2013296. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Li, Z., Du, X., Cao, Y.: Gar: graph assisted reasoning for object detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1295\u20131304 (2020)","DOI":"10.1109\/WACV45572.2020.9093559"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Lin, J., Pan, Y., Lai, R., Yang, X., Chao, H., Yao, T.: Core-Text: improving scene text detection with contrastive relational reasoning. In: International Conference on Multimedia and Expo, pp.\u00a01\u20136. IEEE (2021)","DOI":"10.1109\/ICME51207.2021.9428457"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T., Wang, Y., Liu, X., Qiu, X.: A survey of transformers. AI Open (2022)","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"6_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR36","unstructured":"Liu, S., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR. In: International Conference on Learning Representations (2021)"},{"key":"6_CR37","unstructured":"Liu, S., et\u00a0al.: Detection transformer with stable matching. arXiv preprint arXiv:2304.04742 (2023)"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Liu, S., Huang, D., Wang, Y.: Adaptive NNS: refining pedestrian detection in a crowd. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6459\u20136468 (2019)","DOI":"10.1109\/CVPR.2019.00662"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"6_CR40","unstructured":"Pu, Y., et al.: Rank-DETR for high quality object detection. Adv. Neural Inform. Process. Syst. 36 (2024)"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: International Conference on Computer Vision, pp. 8430\u20138439 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"6_CR42","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Q., Gao, S., Xiong, L., Liang, A., Jiang, K., Zhang, W.: A casting surface dataset and benchmark for subtle and confusable defect detection in complex contexts. IEEE Sensors J. 1 (2024)","DOI":"10.1109\/JSEN.2024.3387082"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. In: AAAI, vol.\u00a036, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Xu, H., Jiang, C., Liang, X., Lin, L., Li, Z.: Reasoning-RCNN: unifying adaptive global reasoning into large-scale object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6419\u20136428 (2019)","DOI":"10.1109\/CVPR.2019.00658"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Ye, M., Ke, L., Li, S., Tai, Y.W., Tang, C.K., Danelljan, M., Yu, F.: Cascade-DETR: delving into high-quality universal object detection. In: International Conference on Computer Vision, pp. 6704\u20136714 (2023)","DOI":"10.1109\/ICCV51070.2023.00617"},{"key":"6_CR47","unstructured":"Zhang, H., et al.: DINO: DETR with improved denoising anchor boxes for end-to-end object detection. In: International Conference on Learning Representations (2022)"},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: Varifocalnet: an iou-aware dense object detector. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"6_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Dense distinct query for end-to-end object detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7329\u20137338 (2023)","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"6_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, C., et al.: Ms-detr: efficient detr training with mixed supervision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17027\u201317036 (2024)","DOI":"10.1109\/CVPR52733.2024.01611"},{"key":"6_CR51","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2020)"},{"key":"6_CR52","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: DETRs with collaborative hybrid assignments training. In: International Conference on Computer Vision, pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72973-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T14:59:27Z","timestamp":1739631567000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72973-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031729720","9783031729737"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72973-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}